Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    mental

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fld
    -0.07
     IPP
    -0.07
     comm
    -0.07
     irm
    -0.07
     Io
    -0.06
    .Part
    -0.06
     waterfall
    -0.06
     уход
    -0.06
    Ids
    -0.06
     يو
    -0.06
    POSITIVE LOGITS
     mental
    0.09
     Mental
    0.08
     Banner
    0.07
    �
    0.07
    ENTE
    0.07
     mentality
    0.07
    τυ
    0.07
    σον
    0.07
    tan
    0.07
    精神
    0.07
    Act Density 0.008%

    No Known Activations